Posts by vladiliescu@mastodon.online
 (DIR) Post #AU4mApQR5Qp6bg5d6O by vladiliescu@mastodon.online
       2023-03-28T13:42:01Z
       
       0 likes, 0 repeats
       
       It's on 🎉.
       
 (DIR) Post #AU4mAs25OQ80h1ij44 by vladiliescu@mastodon.online
       2023-03-28T13:42:59Z
       
       0 likes, 1 repeats
       
       😕
       
 (DIR) Post #AVYIrhpg5sAZGOscO8 by vladiliescu@mastodon.online
       2023-05-11T17:27:34Z
       
       0 likes, 0 repeats
       
       @simon That's a really interesting attack! I was wondering if/how delimiters can be broken, I had no idea a model might be convinced the instruction has been satisfied. Curious if this happens only to OpenAI models, or if LLaMA/PaLM are susceptible as well.
       
 (DIR) Post #AVYTfAqY0Yb8ypVtrM by vladiliescu@mastodon.online
       2023-05-11T19:28:37Z
       
       0 likes, 0 repeats
       
       @simon Tried them against GPT-4 and it seems to resist them, at least in Azure's OpenAI Studio.The system prompt was pretty basic -- "You are an AI assistant that helps people find information.", not sure if it affects the output.
       
 (DIR) Post #AVZYHvThfvcfaHWRJg by vladiliescu@mastodon.online
       2023-05-12T07:55:20Z
       
       0 likes, 0 repeats
       
       @simon Agreed, [system] prompts are quite powerful - I've managed to prompt inject Bing (which afaik is based on GPT-4) and have it start each conversation with claiming it's Chandler Bing and then telling a joke. All this by having a page open while invoking the sidebar (no instructions needed to have it read the page).Makes me wonder how it would behave if we scrubbed the input of [system] prompts too (I know, I know, it's not a definitive solution either :) )https://vladiliescu.net/bing-becomes-chandler/
       
 (DIR) Post #AZh3gxecmqA0U5oLqK by vladiliescu@mastodon.online
       2023-09-12T14:20:05Z
       
       0 likes, 0 repeats
       
       @tante This why system prompts are so useful, and why LLMs need time (i.e. tokens) to think. Using GPT-4, if you were to add "Explain your reasoning and then provide the answer." to the system prompt, it would provide the right answer.> Each brother has 2 sisters, and Sally is one of those sisters. Since all 3 brothers have the same 2 sisters, there are only 2 sisters in total. Sally is one of these sisters, so she has 1 other sister.